A population-based SHM methodology for heterogeneous structures: Transferring damage localisation knowledge between different aircraft wings. (1st June 2022)

• Record Type: Journal Article
• Authors: Gardner, P.; Bull, L.A.; Gosliga, J.; Poole, J.; Dervilis, N.; Worden, K.
• Is Part Of: Mechanical systems and signal processing. Volume 172(2022)
• Publication Date: 2022-06-01
• Subjects: Population-based structural health monitoring -- Irreducible elements -- Attributed graphs -- Transfer learning -- Domain adaptation; Structural dynamics -- Periodicals; Vibration -- Periodicals; Constructions -- Dynamique -- Périodiques; Vibration -- Périodiques; Structural dynamics; Vibration; Periodicals; 621
• DOI: 10.1016/j.ymssp.2022.108918
• Languages: English
• ISSNs: 0888-3270

Abstract

Abstract: Population-based structural health monitoring (PBSHM) offers a new viewpoint for structural health monitoring (SHM), allowing diagnostic information to be shared across populations of structures. By extending the set of available damage observations, a population-based approach can diagnose damage previously unseen on a structure of interest by leveraging damage information from other structures in the population. These technologies therefore provide significant benefits for making SHM practicable in a variety of industrial settings. It is proposed that PBSHM methodologies must be comprised of tools to assess similarity coupled with algorithms that perform knowledge transfer . The similarity tools are important for identifying whether an SHM task should be attempted for a given population by assessing both the structural similarities between members of a population and similarities in their data spaces. An abstract representation of structures in a graphical domain is presented as an objective way of assessing structural similarity, with distance metrics utilised for assessing data-space similarities. Knowledge transfer is performed using a branch of transfer learning called domain adaptation . By determining if members of a population are similar in a structural and data-space sense, the risk of negative transfer can be reduced; whereby domain adaptation reduces classification performance. This paper demonstrates a PBSHM methodology for transferring knowledge within a heterogeneous population (a group of non-identical structures). Specifically, the PBSHM methodology is shown to transfer localisation labels from a Gnat aircraft wing to an unlabelled Piper Tomahawk aircraft wing dataset, resulting in 100% classification accuracy. Graphical abstract: Highlights: A population-based SHM methodology is presented for heterogeneous populations. Methodology quantifies structural and data similarity before knowledge transfer. Abstract representations of structures as graphs quantify structural similarity. Domain adaptation transfers label knowledge between structures. The methodology is demonstrated on a population of two experimental aircraft wings.